pith. sign in
Pith Number

pith:DVLRP5ZA

pith:2026:DVLRP5ZARWHODSGCPVWJ2GGYHP
not attested not anchored not stored refs resolved

ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery

Andrew Y. Zhou, Michael K. Gilson, Peter Eckmann, Rose Yu, Sharvaree Vadgama, Sumanth Varambally

ToolMol pairs an LLM agent with RDKit tools inside a genetic algorithm to generate drug ligands that show stronger predicted binding than earlier methods.

arxiv:2605.12784 v2 · 2026-05-12 · cs.LG · cs.NE · q-bio.QM

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{DVLRP5ZARWHODSGCPVWJ2GGYHP}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

ToolMol achieves state-of-the-art performance on multi-objective property optimization tasks, discovering drug-like and synthesizable ligands that have >10% stronger predicted binding affinity compared to existing methods, evaluated on three protein targets. ToolMol ligands additionally achieve state-of-the-art results in gold-standard Absolute Binding Free Energy scores, gaining over existing methods by over 35%.

C2weakest assumption

The assumption that the agentic LLM operator, when equipped with the RDKit toolbox, can consistently execute precise and unbiased ligand modifications that genuinely improve multi-objective fitness without introducing selection biases or invalid structures that undermine the genetic algorithm's search.

C3one line summary

ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets.

References

46 extracted · 46 resolved · 5 Pith anchors

[1] Quantifying the Chemical Beauty of Drugs 2012 · doi:10.1038/nchem.1243
[2] A., MacKnight, R., Kline, B., and Gomes, G 2023
[3] ChemCrow: Augmenting large-language models with chemistry tools 2023 · arXiv:2304.05376
[4] El Agente Estructural: An Artificially Intelligent Molecular Editor 2026 · arXiv:2602.04849
[5] A., Fernandez Prada, D 2024 · doi:10.3389/frhem.2024.1305741
Receipt and verification
First computed 2026-05-18T03:09:13.082995Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

1d5717f7208d8ee1c8c27d6c9d18d83bd93538042b7f2d81c2a46d6412419fc3

Aliases

arxiv: 2605.12784 · arxiv_version: 2605.12784v2 · doi: 10.48550/arxiv.2605.12784 · pith_short_12: DVLRP5ZARWHO · pith_short_16: DVLRP5ZARWHODSGC · pith_short_8: DVLRP5ZA
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/DVLRP5ZARWHODSGCPVWJ2GGYHP \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 1d5717f7208d8ee1c8c27d6c9d18d83bd93538042b7f2d81c2a46d6412419fc3
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "183d032fb2a149c2fdec77c716384e863ca0116d474c6b4a16dc8e4e9aacb880",
    "cross_cats_sorted": [
      "cs.NE",
      "q-bio.QM"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T21:58:14Z",
    "title_canon_sha256": "3b0f22d4f78f908926d79b6342cf94213293ef053f4a62a90d37ed0b98edbd22"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12784",
    "kind": "arxiv",
    "version": 2
  }
}